const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
unsigned char *ptr = ack_skb->h.raw + TCP_SKB_CB(ack_skb)->sacked;
- struct tcp_sack_block *sp = (struct tcp_sack_block *)(ptr+2);
+ struct tcp_sack_block_wire *sp = (struct tcp_sack_block_wire *)(ptr+2);
+ struct sk_buff *cached_skb;
int num_sacks = (ptr[1] - TCPOLEN_SACK_BASE)>>3;
int reord = tp->packets_out;
int prior_fackets;
u32 lost_retrans = 0;
int flag = 0;
int dup_sack = 0;
+ int cached_fack_count;
int i;
+ int first_sack_index;
if (!tp->sacked_out)
tp->fackets_out = 0;
prior_fackets = tp->fackets_out;
+ /* Check for D-SACK. */
+ if (before(ntohl(sp[0].start_seq), TCP_SKB_CB(ack_skb)->ack_seq)) {
+ dup_sack = 1;
+ tp->rx_opt.sack_ok |= 4;
+ NET_INC_STATS_BH(LINUX_MIB_TCPDSACKRECV);
+ } else if (num_sacks > 1 &&
+ !after(ntohl(sp[0].end_seq), ntohl(sp[1].end_seq)) &&
+ !before(ntohl(sp[0].start_seq), ntohl(sp[1].start_seq))) {
+ dup_sack = 1;
+ tp->rx_opt.sack_ok |= 4;
+ NET_INC_STATS_BH(LINUX_MIB_TCPDSACKOFORECV);
+ }
+
+ /* D-SACK for already forgotten data...
+ * Do dumb counting. */
+ if (dup_sack &&
+ !after(ntohl(sp[0].end_seq), prior_snd_una) &&
+ after(ntohl(sp[0].end_seq), tp->undo_marker))
+ tp->undo_retrans--;
+
+ /* Eliminate too old ACKs, but take into
+ * account more or less fresh ones, they can
+ * contain valid SACK info.
+ */
+ if (before(TCP_SKB_CB(ack_skb)->ack_seq, prior_snd_una - tp->max_window))
+ return 0;
+
/* SACK fastpath:
* if the only SACK change is the increase of the end_seq of
* the first block then only apply that SACK block
* and use retrans queue hinting otherwise slowpath */
flag = 1;
- for (i = 0; i< num_sacks; i++) {
- __u32 start_seq = ntohl(sp[i].start_seq);
- __u32 end_seq = ntohl(sp[i].end_seq);
+ for (i = 0; i < num_sacks; i++) {
+ __be32 start_seq = sp[i].start_seq;
+ __be32 end_seq = sp[i].end_seq;
- if (i == 0){
+ if (i == 0) {
if (tp->recv_sack_cache[i].start_seq != start_seq)
flag = 0;
} else {
}
tp->recv_sack_cache[i].start_seq = start_seq;
tp->recv_sack_cache[i].end_seq = end_seq;
-
- /* Check for D-SACK. */
- if (i == 0) {
- u32 ack = TCP_SKB_CB(ack_skb)->ack_seq;
-
- if (before(start_seq, ack)) {
- dup_sack = 1;
- tp->rx_opt.sack_ok |= 4;
- NET_INC_STATS_BH(LINUX_MIB_TCPDSACKRECV);
- } else if (num_sacks > 1 &&
- !after(end_seq, ntohl(sp[1].end_seq)) &&
- !before(start_seq, ntohl(sp[1].start_seq))) {
- dup_sack = 1;
- tp->rx_opt.sack_ok |= 4;
- NET_INC_STATS_BH(LINUX_MIB_TCPDSACKOFORECV);
- }
-
- /* D-SACK for already forgotten data...
- * Do dumb counting. */
- if (dup_sack &&
- !after(end_seq, prior_snd_una) &&
- after(end_seq, tp->undo_marker))
- tp->undo_retrans--;
-
- /* Eliminate too old ACKs, but take into
- * account more or less fresh ones, they can
- * contain valid SACK info.
- */
- if (before(ack, prior_snd_una - tp->max_window))
- return 0;
- }
+ }
+ /* Clear the rest of the cache sack blocks so they won't match mistakenly. */
+ for (; i < ARRAY_SIZE(tp->recv_sack_cache); i++) {
+ tp->recv_sack_cache[i].start_seq = 0;
+ tp->recv_sack_cache[i].end_seq = 0;
}
+ first_sack_index = 0;
if (flag)
num_sacks = 1;
else {
for (j = 0; j < i; j++){
if (after(ntohl(sp[j].start_seq),
ntohl(sp[j+1].start_seq))){
- sp[j].start_seq = htonl(tp->recv_sack_cache[j+1].start_seq);
- sp[j].end_seq = htonl(tp->recv_sack_cache[j+1].end_seq);
- sp[j+1].start_seq = htonl(tp->recv_sack_cache[j].start_seq);
- sp[j+1].end_seq = htonl(tp->recv_sack_cache[j].end_seq);
+ struct tcp_sack_block_wire tmp;
+
+ tmp = sp[j];
+ sp[j] = sp[j+1];
+ sp[j+1] = tmp;
+
+ /* Track where the first SACK block goes to */
+ if (j == first_sack_index)
+ first_sack_index = j+1;
}
}
/* clear flag as used for different purpose in following code */
flag = 0;
+ /* Use SACK fastpath hint if valid */
+ cached_skb = tp->fastpath_skb_hint;
+ cached_fack_count = tp->fastpath_cnt_hint;
+ if (!cached_skb) {
+ cached_skb = sk->sk_write_queue.next;
+ cached_fack_count = 0;
+ }
+
for (i=0; i<num_sacks; i++, sp++) {
struct sk_buff *skb;
__u32 start_seq = ntohl(sp->start_seq);
__u32 end_seq = ntohl(sp->end_seq);
int fack_count;
- /* Use SACK fastpath hint if valid */
- if (tp->fastpath_skb_hint) {
- skb = tp->fastpath_skb_hint;
- fack_count = tp->fastpath_cnt_hint;
- } else {
- skb = sk->sk_write_queue.next;
- fack_count = 0;
- }
+ skb = cached_skb;
+ fack_count = cached_fack_count;
/* Event "B" in the comment above. */
if (after(end_seq, tp->high_seq))
int in_sack, pcount;
u8 sacked;
- tp->fastpath_skb_hint = skb;
- tp->fastpath_cnt_hint = fack_count;
+ cached_skb = skb;
+ cached_fack_count = fack_count;
+ if (i == first_sack_index) {
+ tp->fastpath_skb_hint = skb;
+ tp->fastpath_cnt_hint = fack_count;
+ }
/* The retransmission queue is always in order, so
* we can short-circuit the walk early.
return acked;
}
-static u32 tcp_usrtt(const struct sk_buff *skb)
+static u32 tcp_usrtt(struct timeval *tv)
{
- struct timeval tv, now;
+ struct timeval now;
do_gettimeofday(&now);
- skb_get_timestamp(skb, &tv);
- return (now.tv_sec - tv.tv_sec) * 1000000 + (now.tv_usec - tv.tv_usec);
+ return (now.tv_sec - tv->tv_sec) * 1000000 + (now.tv_usec - tv->tv_usec);
}
/* Remove acknowledged frames from the retransmission queue. */
u32 pkts_acked = 0;
void (*rtt_sample)(struct sock *sk, u32 usrtt)
= icsk->icsk_ca_ops->rtt_sample;
+ struct timeval tv = { .tv_sec = 0, .tv_usec = 0 };
while ((skb = skb_peek(&sk->sk_write_queue)) &&
skb != sk->sk_send_head) {
seq_rtt = -1;
} else if (seq_rtt < 0) {
seq_rtt = now - scb->when;
- if (rtt_sample)
- (*rtt_sample)(sk, tcp_usrtt(skb));
+ skb_get_timestamp(skb, &tv);
}
if (sacked & TCPCB_SACKED_ACKED)
tp->sacked_out -= tcp_skb_pcount(skb);
}
} else if (seq_rtt < 0) {
seq_rtt = now - scb->when;
- if (rtt_sample)
- (*rtt_sample)(sk, tcp_usrtt(skb));
+ skb_get_timestamp(skb, &tv);
}
tcp_dec_pcount_approx(&tp->fackets_out, skb);
tcp_packets_out_dec(tp, skb);
if (acked&FLAG_ACKED) {
tcp_ack_update_rtt(sk, acked, seq_rtt);
tcp_ack_packets_out(sk, tp);
+ if (rtt_sample && !(acked & FLAG_RETRANS_DATA_ACKED))
+ (*rtt_sample)(sk, tcp_usrtt(&tv));
if (icsk->icsk_ca_ops->pkts_acked)
icsk->icsk_ca_ops->pkts_acked(sk, pkts_acked);
switch(opcode) {
case TCPOPT_MSS:
if(opsize==TCPOLEN_MSS && th->syn && !estab) {
- u16 in_mss = ntohs(get_unaligned((__u16 *)ptr));
+ u16 in_mss = ntohs(get_unaligned((__be16 *)ptr));
if (in_mss) {
if (opt_rx->user_mss && opt_rx->user_mss < in_mss)
in_mss = opt_rx->user_mss;
if ((estab && opt_rx->tstamp_ok) ||
(!estab && sysctl_tcp_timestamps)) {
opt_rx->saw_tstamp = 1;
- opt_rx->rcv_tsval = ntohl(get_unaligned((__u32 *)ptr));
- opt_rx->rcv_tsecr = ntohl(get_unaligned((__u32 *)(ptr+4)));
+ opt_rx->rcv_tsval = ntohl(get_unaligned((__be32 *)ptr));
+ opt_rx->rcv_tsecr = ntohl(get_unaligned((__be32 *)(ptr+4)));
}
}
break;
opt_rx->sack_ok) {
TCP_SKB_CB(skb)->sacked = (ptr - 2) - (unsigned char *)th;
}
+#ifdef CONFIG_TCP_MD5SIG
+ case TCPOPT_MD5SIG:
+ /*
+ * The MD5 Hash has already been
+ * checked (see tcp_v{4,6}_do_rcv()).
+ */
+ break;
+#endif
};
ptr+=opsize-2;
length-=opsize;
return 0;
} else if (tp->rx_opt.tstamp_ok &&
th->doff == (sizeof(struct tcphdr)>>2)+(TCPOLEN_TSTAMP_ALIGNED>>2)) {
- __u32 *ptr = (__u32 *)(th + 1);
- if (*ptr == ntohl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16)
+ __be32 *ptr = (__be32 *)(th + 1);
+ if (*ptr == htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16)
| (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP)) {
tp->rx_opt.saw_tstamp = 1;
++ptr;
return err;
}
-static int __tcp_checksum_complete_user(struct sock *sk, struct sk_buff *skb)
+static __sum16 __tcp_checksum_complete_user(struct sock *sk, struct sk_buff *skb)
{
- int result;
+ __sum16 result;
if (sock_owned_by_user(sk)) {
local_bh_enable();
/* Check timestamp */
if (tcp_header_len == sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) {
- __u32 *ptr = (__u32 *)(th + 1);
+ __be32 *ptr = (__be32 *)(th + 1);
/* No? Slow path! */
- if (*ptr != ntohl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16)
+ if (*ptr != htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16)
| (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP))
goto slow_path;
* Change state from SYN-SENT only after copied_seq
* is initialized. */
tp->copied_seq = tp->rcv_nxt;
- mb();
+ smp_mb();
tcp_set_state(sk, TCP_ESTABLISHED);
+ security_inet_conn_established(sk, skb);
+
/* Make sure socket is routed, for correct metrics. */
icsk->icsk_af_ops->rebuild_header(sk);
* But, this leaves one open to an easy denial of
* service attack, and SYN cookies can't defend
* against this problem. So, we drop the data
- * in the interest of security over speed.
+ * in the interest of security over speed unless
+ * it's still in use.
*/
- goto discard;
+ kfree_skb(skb);
+ return 0;
}
goto discard;
case TCP_SYN_RECV:
if (acceptable) {
tp->copied_seq = tp->rcv_nxt;
- mb();
+ smp_mb();
tcp_set_state(sk, TCP_ESTABLISHED);
sk->sk_state_change(sk);